Knowledge Graph-based Thought: a knowledge graph enhanced LLMs framework for pan-cancer question answering

Background In recent years, Large Language Models (LLMs) have shown promise in various domains, notably in biomedical sciences. However, their real-world application is often limited by issues like erroneous outputs and hallucinatory responses. Results We developed the Knowledge Graph-based Thought (KGT) framework, an innovative solution that integrates LLMs with Knowledge Graphs (KGs) to improve their initial responses by utilizing verifiable information from KGs, thus significantly reducing factual errors in reasoning. The KGT framework demonstrates strong adaptability and performs well across various open-source LLMs. Notably, KGT can facilitate the discovery of new uses for existing drugs through potential drug-cancer associations, and can assist in predicting resistance by analyzing relevant biomarkers and genetic mechanisms. To evaluate the Knowledge Graph Question Answering task within biomedicine, we utilize a pan-cancer knowledge graph to develop a pan-cancer question answering benchmark, named the Pan-cancer Question Answering (PcQA). Conclusions The KGT framework substantially improves the accuracy and utility of LLMs in the biomedical field, demonstrating its exceptional performance in biomedical question answering. Key Points ### Competing Interest Statement The authors have declared no competing interest. * KG : knowledge graph LLM : large language model NLP : natural language processing SFT : supervised fine-tuning RLHF : reinforcement learning with human feedback CF : catastrophic forgetting CoT : Chain-of-thought APE : automatic prompt engineer KGQA : knowledge graph question answering BFS : breadth-first search PcQA : Pan-cancer Question Answering ICL : in-context learning GPT : generative pre-trained transformer.